Duplicate from bleysg/Phind-CodeLlama-34B-v2

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Phind-CodeLlama-34B-v2
+emoji: 🔍
+colorFrom: orange
+colorTo: purple
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+pinned: false
+duplicated_from: bleysg/Phind-CodeLlama-34B-v2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,119 @@
+import os
+import re
+import logging
+import gradio as gr
+import openai
+
+print(os.environ)
+openai.api_base = os.environ.get("OPENAI_API_BASE")
+openai.api_key = os.environ.get("OPENAI_API_KEY")
+
+BASE_SYSTEM_MESSAGE = """### System Prompt\n"""
+
+def make_prediction(prompt, max_tokens=None, temperature=None, top_p=None, top_k=None, repetition_penalty=None):
+    completion = openai.Completion.create(model="Phind/Phind-CodeLlama-34B-v2", prompt=prompt, max_tokens=max_tokens, temperature=temperature, top_p=top_p, top_k=top_k, repetition_penalty=repetition_penalty, stream=True, stop=["</s>", "<|im_end|>"])
+    for chunk in completion:
+        yield chunk["choices"][0]["text"]
+
+
+def clear_chat(chat_history_state, chat_message):
+    chat_history_state = []
+    chat_message = ''
+    return chat_history_state, chat_message
+
+
+def user(message, history):
+    history = history or []
+    # Append the user's message to the conversation history
+    history.append([message, ""])
+    return "", history
+
+
+def chat(history, system_message, max_tokens, temperature, top_p, top_k, repetition_penalty):
+    history = history or []
+
+    messages = BASE_SYSTEM_MESSAGE + system_message.strip() + "\n" + \
+               "\n".join(["\n".join(["### User Message\n"+item[0]+"\n\n", "### Assistant\n"+item[1]+"\n\n"])
+                          for item in history])
+    # strip the last `<|end_of_turn|>` from the messages
+    #messages = messages.rstrip("<|end_of_turn|>")
+    # remove last space from assistant, some models output a ZWSP if you leave a space
+    messages = messages.rstrip()
+
+    prediction = make_prediction(
+        messages,
+        max_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        top_k=top_k,
+        repetition_penalty=repetition_penalty,
+    )
+    for tokens in prediction:
+        tokens = re.findall(r'(.*?)(\s|$)', tokens)
+        for subtoken in tokens:
+            subtoken = "".join(subtoken)
+            # Remove "Response\n" if it's at the beginning of the assistant's output
+            if subtoken.startswith("Response"):
+                subtoken = subtoken[len("Response"):]
+            answer = subtoken
+            history[-1][1] += answer
+            # stream the response
+            yield history, history, ""
+
+
+start_message = ""
+
+CSS ="""
+.contain { display: flex; flex-direction: column; }
+.gradio-container { height: 100vh !important; }
+#component-0 { height: 100%; }
+#chatbot { flex-grow: 1; overflow: auto; resize: vertical; }
+"""
+
+#with gr.Blocks() as demo:
+with gr.Blocks(css=CSS) as demo:
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown(f"""
+                    ## This demo is an unquantized GPU chatbot of [Phind-CodeLlama-34B-v2](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2)
+                    Brought to you by your friends at Alignment Lab AI, garage-bAInd, Open Access AI Collective, and OpenChat!
+                    """)
+    with gr.Row():
+        gr.Markdown("# 🔍 Phind CodeLlama 34B Playground Space! 🔎")
+    with gr.Row():
+        #chatbot = gr.Chatbot().style(height=500)
+        chatbot = gr.Chatbot(elem_id="chatbot")
+    with gr.Row():
+        message = gr.Textbox(
+            label="What do you want to chat about?",
+            placeholder="Ask me anything.",
+            lines=3,
+        )
+    with gr.Row():
+        submit = gr.Button(value="Send message", variant="secondary").style(full_width=True)
+        clear = gr.Button(value="New topic", variant="secondary").style(full_width=False)
+        stop = gr.Button(value="Stop", variant="secondary").style(full_width=False)
+    with gr.Accordion("Show Model Parameters", open=False):
+        with gr.Row():
+            with gr.Column():
+                max_tokens = gr.Slider(20, 4000, label="Max Tokens", step=20, value=2000)
+                temperature = gr.Slider(0.0, 2.0, label="Temperature", step=0.1, value=0.8)
+                top_p = gr.Slider(0.0, 1.0, label="Top P", step=0.02, value=0.95)
+                top_k = gr.Slider(-1, 100, label="Top K", step=1, value=40)
+                repetition_penalty = gr.Slider(0.0, 2.0, label="Repetition Penalty", step=0.05, value=1.1)
+
+        system_msg = gr.Textbox(
+            start_message, label="System Message", interactive=True, visible=True, placeholder="System prompt. Provide instructions which you want the model to remember.", lines=5)
+
+    chat_history_state = gr.State()
+    clear.click(clear_chat, inputs=[chat_history_state, message], outputs=[chat_history_state, message], queue=False)
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+    submit_click_event = submit.click(
+        fn=user, inputs=[message, chat_history_state], outputs=[message, chat_history_state], queue=True
+    ).then(
+        fn=chat, inputs=[chat_history_state, system_msg, max_tokens, temperature, top_p, top_k, repetition_penalty], outputs=[chatbot, chat_history_state, message], queue=True
+    )
+    stop.click(fn=None, inputs=None, outputs=None, cancels=[submit_click_event], queue=False)
+
+demo.queue(max_size=48, concurrency_count=8).launch(debug=True, server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,2 @@
+requests
+openai